
Principal Forward Deployment Engineer
Posted 15 days ago
The role in short
Lead a forward-deployed AI squad to design, build, and ship production-grade agentic AI systems and RAG pipelines for enterprise clients.
Role description
Principal Forward Deployment Engineer
The Role
We are seeking a Principal Forward Deployment Engineer to join our UST-PACE SEALS (Solution Engineering and Architecture Leadership) organization. In this role, you will lead a small, forward-deployed AI squad embedded directly at enterprise client sites. You will personally design, build, and ship production-grade agentic AI systems, while owning engagements from the first sprint through signed closeout. You will architect context engineering frameworks, design RAG pipelines, build and orchestrate multi-agent systems, and deploy them to production runtimes including Amazon Bedrock AgentCore. You will establish KPI baselines, drive delivery against committed outcomes, and leave clients with working agents in production and the capability to scale independently. The ideal candidate is a hands-on engineering leader who writes Python every day, has shipped agentic systems against real enterprise data, and can operate decisively within complex enterprise environments.
What You’ll Do
- Lead and personally contribute to the design and delivery of production agentic AI systems across the full AI-Native SDLC.
- Own engagement governance, including sprint cadence, scope control, KPI baseline definition, and progress against committed outcomes.
- Architect context engineering frameworks, including system prompts, domain knowledge bases, agent instruction sets, and structured context documents.
- Design and implement end-to-end RAG pipelines, including data ingestion, chunking strategies, embedding model selection, vector store configuration, and retrieval quality evaluation.
- Build and orchestrate multi-agent systems using Strands Agents, LangGraph, CrewAI, AutoGen, or similar frameworks.
- Deploy and operate agents on Amazon Bedrock AgentCore, including Runtime, Memory, Gateway, and Observability services.
- Design agent memory architectures covering short-term session memory, long-term persistent memory, and semantic memory stores.
- Implement semantic caching, prompt caching, response caching, and KV-cache optimization to improve latency and control inference costs.
- Manage token costs through model selection, context window optimization, prompt compression, cost telemetry, and benchmarking.
- Select foundation models based on capability, latency, cost, and compliance requirements across Claude, Amazon Nova, GPT-4o, Llama, and Gemini.
- Implement end-to-end agent observability, including traces, spans, latency, token usage, error rates, and decision audit logs.
- Design and build MCP servers connecting agents to enterprise APIs, data systems, ITSM, CMDB, Git, CI/CD, and observability platforms.
- Serve as the technical point of contact for VP-level client sponsors and translate engineering realities into clear business value.
- Own engagement closeout, including scope delivered, KPI measurement, artifact handover, and client sponsor sign-off.
- Mentor FDE Builders and contribute reusable prompts, agent configurations, memory patterns, and cost benchmarks back into the AI Engineering practice.
This position description identifies the responsibilities and tasks typically associated with the performance of the position. Other relevant essential functions may be required.
What You Need
Required
- 10–14 years of total technology experience.
- At least 3 years of experience designing and deploying production agentic AI or LLM-based systems.
- Strong Python expertise with hands-on experience shipping production-grade code.
- Deep hands-on experience in Context Engineering and Prompt Engineering.
- Production experience designing and implementing RAG pipelines.
- Experience with vector databases such as Pinecone, Weaviate, pgvector, or equivalent.
- Hands-on experience building and orchestrating multi-agent systems using Strands Agents, LangGraph, LangChain, CrewAI, AutoGen, or similar frameworks.
- Experience deploying and operating agents on Amazon Bedrock AgentCore, including Runtime, Memory, Gateway, and Observability.
- Strong experience with agent memory management, including session, semantic, summarization, and long-term memory.
- Experience implementing semantic caching, prompt caching, KV-cache optimization, and response caching.
- Strong understanding of token cost management, context window optimization, model routing, prompt compression, and cost telemetry.
- Experience working with foundation models such as Claude, Amazon Nova, GPT-4o, Llama, and Gemini and understanding capability, latency, and cost trade-offs.
- Experience with agent observability tools such as LangSmith, Arize, AgentCore Observability, Helicone, or equivalent.
- Experience with MCP server design and integration patterns.
- Experience with AWS, Azure, or GCP and containerized agent deployment patterns.
- Proven technical leadership experience on customer-facing AI delivery engagements.
- Bachelor's degree in Computer Science, Engineering, a related field, or equivalent practical experience.
Preferred
- Experience leading short-cycle, fixed-scope AI delivery engagements with measurable production outcomes and defined exit criteria.
- Familiarity with AI governance frameworks, Responsible AI tooling, and enterprise AI usage policy design.
- Familiarity with SOC 2 and FedRAMP as they apply to AI system deployments.
- Contributions to the AI engineering community through open-source agent projects, technical writing, or conference speaking.
- Relevant cloud or AI/ML certifications such as AWS ML Specialty, Azure AI Engineer, or Google Professional ML Engineer.
Key Competencies
- Production Engineering Rigor: Treats observability, cost management, and memory design as first-class engineering concerns.
- Player-Conductor Mindset: Leads by doing and ships production code alongside the team every sprint.
- Client Independence: Engineers the client's ability to operate and scale independently from day one.
- Executive Communication: Translates engineering complexity into clear business narratives without losing technical precision.
- Delivery Focus: Thrives under fixed-scope, time-boxed delivery pressure.
- Continuous Innovation: Experiments with emerging agent frameworks, model families, and cost optimization techniques.
- Cross-Functional Leadership: Builds trust with both VP-level sponsors and engineering teams.
Location & Compensation
Compensation can differ depending on factors including but not limited to the specific office location, role, skill set, education, and level of experience. UST provides a reasonable range of compensation for roles that may be hired in various U.S. markets as set forth below.
Role Location: St. Louis, Missouri
Compensation Range: $122000- $183000
Who We Are
Since 1999, UST has worked side by side with the world’s best companies to make a powerful impact through transformation. Headquartered in the United States, UST is powered by technology, driven by AI, inspired by people, and led by our purpose, we partner with our clients from design to operation. Our AI-driven digital solutions, proprietary platforms, engineering, R&D, products, and innovation ecosystem turn core challenges into impactful, disruptive business outcomes. With deep industry knowledge and a future-ready mindset, we infuse expertise, innovation, and agility into our clients’ organizations—delivering measurable value and positive lasting change for them, their customers, and communities around the world. Together, with 30,000+ employees in 30+ countries, we build for boundless impact—touching billions of lives in the process. Visit us at .
Benefits
Full-time, regular employees accrue a minimum of 10 days of paid vacation per year, receive 6 days of paid sick leave each year (pro-rated for new hires throughout the year), 10 paid holidays, and are eligible for paid bereavement leave and jury duty. They are eligible to participate in the Company’s 401(k) Retirement Plan with employer matching. They and their dependents residing in the US are eligible for medical, dental, and vision insurance, as well as the following Company-paid Employee Only benefits: basic life insurance, accidental death and disability insurance, and short- and long-term disability benefits. Regular employees may purchase additional voluntary short-term disability benefits, and participate in a Health Savings Account (HSA) as well as a Flexible Spending Account (FSA) for healthcare, dependent child care, and/or commuting expenses as allowable under IRS guidelines. Benefits offerings vary in Puerto Rico.
Part-time employees receive 6 days of paid sick leave each year (pro-rated for new hires throughout the year) and are eligible to participate in the Company’s 401(k) Retirement Plan with employer matching.
Full-time temporary employees receive 6 days of paid sick leave each year (pro-rated for new hires throughout the year) and are eligible to participate in the Company’s 401(k) program with employer matching. They and their dependents residing in the US are eligible for medical, dental, and vision insurance.
Part-time temporary employees receive 6 days of paid sick leave each year (pro-rated for new hires throughout the year).
All US employees who work in a state or locality with more generous paid sick leave benefits than specified here will receive the benefit of those sick leave laws.
As part of our recruitment process, UST may use AI or automated tools to support activities such as application screening, scheduling, or interview assistance . All hiring decisions are made by our recruitment team. Where applicable law requires it, further notice will be provided separately.
Equal Employment Opportunity Statement
UST is an Equal Opportunity Employer.
All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, status as a protected veteran, or any other applicable characteristics protected by law. We will consider qualified applicants with arrest or conviction records in accordance with state and local laws and “fair chance” ordinances.
UST reserves the right to periodically redefine your roles and responsibilities based on the requirements of the organization and/or your performance.
#UST
Skills
Agentic AI, Cloud Infrastructure, Context Engineering, Arize
Benefits
Compensation range: $ 122,000.00 to 183,000.00 per year
Prep for this interview
4 questions likely to come up at UST, each matched to a line in this posting.
- 1Cloud, deployment and security
They wrote: “Experience with AWS, Azure, or GCP and containerized agent deployment patterns.”
How would you debug a deployment that works in staging but fails at the customer's site?
How to answer
Why they ask: Customer environments differ in ways you can't see. This tests method under pressure.
- Compare versions, config and environment variables
- Check network rules, proxies and certificates (common in enterprise)
- Look at resource limits and permissions
- Add the missing check to your install steps afterwards
Tip: List the usual suspects and how you'd check each without full access.
- 2Integrations and APIs
They wrote: “Design and build MCP servers connecting agents to enterprise APIs, data systems, ITSM, CMDB, Git, CI/CD, and observability platforms.”
Walk me through connecting our product to a customer's internal system that has no documentation.
How to answer
Why they ask: This happens weekly in the job. They want a calm, step-by-step method.
- Find who owns the system and get read access to a test environment
- Watch real traffic or logs to learn the data shapes
- Build a thin adapter with logging around every call
- Agree on how failures get reported, and who fixes what
Tip: Talk about finding the owner of the system first. The code is the easy part.
- 3LLMs, RAG and agents
They wrote: “Lead and personally contribute to the design and delivery of production agentic AI systems across the full AI-Native SDLC.”
When would you use an agent that takes actions, and how do you keep it safe?
How to answer
Why they ask: Agent work is growing fast in FDE postings. Senior candidates are expected to know where agents fail.
- Use agents for multi-step tasks with clear success checks; avoid them where one wrong action is costly
- Give the agent narrow tools and permissions, not broad access
- Require human approval for risky actions
- Log every step so the customer can audit it
Tip: Start from the cost of a wrong action. Limit what the agent can do, and log everything.
- 4Coding
They wrote: “Strong Python expertise with hands-on experience shipping production-grade code.”
Here's a CSV export from a customer. Write a script that cleans it and loads it into our API.
How to answer
Why they ask: Very close to real FDE work. They watch how you handle bad rows and failures.
- Read with a proper CSV parser; check the header first
- Validate each row and collect errors, not crash on the first one
- Send in batches with retries and a clear report at the end
- Write one or two quick tests for the parsing
Tip: Talk through edge cases out loud: encodings, missing fields, duplicates, rate limits.
Not the one? Get the next one by email
New roles land here every day. Pick what you want to hear about.
Want the job, not just the posting? Learn how FDEs work.
FDE Info is our free weekly newsletter for forward deployed engineers: tools, field notes from real deployments, and how FDE teams hire and pay.
Free. One email a week. Unsubscribe in one click.