As a Senior ML Engineer, you build production grade multi agentic systems that guide people through complex, high‑stakes conversations. Our systems combine multi‑step agent orchestration, retrieval, memory, and rigorous evaluation and safety layers.
We're looking for a Senior ML Engineer to design, build, tune, and evaluate these agentic systems end to end — from contex t engineering and tool design, through retrieval and memory, to evaluation and safety guardrails. This is an applied‑ML and LLM‑systems role focused on agent behavior, model selection, retrieval of quality, and evaluation.
Though understanding of AI/ML is crucial for this role, we kindly request that you refrain from using GenAI while going through the interview process to allow fair evaluation of your skillset.
What you’ll do
- Design and orchestrate multi-agentic workflows .
- Own context engineeringfor production agents, including system design, safety rules, context injection, and clarifying question strategies.
- Design tool s and function-calling interfaces, so agents take reliable, well-structured actions.
- Build and tune retrieval (RAG) pipelines— embeddings, vector search, filtering, query rewriting, and relevance tuning.
- Select and optimize modelsacross providers, balance quality, latency, determinism, and cost.
- Design agent memory and context managementfor coherent multi-turn behavior.
- Build safety and guardrail layers for input filtering, scope and safety checks, and graceful handling of edge cases.
- Own LLM evaluation, offline eval suites, graders/LLM-as-judge, test sets and personas, metrics, and quality gates.
- Collaborate with cross-functional stakeholders on requirements, project execution and status tracking.
- Meta technical responsibility: Document high-fidelity technical designs, establish alignment on solutions within broader engineering team.
What we’re looking for
- Bachelor's or master's degree in data science , Machine Learning Engineering, or a related technical field, or equivalent practical experience.
- 5+ years of professional Data Science/ML engineering experience.
- Strong applied experience buildingLLM-powered agents in production— shipped, multi-turn agentic systems, not just prompt experiments.
- Hands-on expertise withagent orchestration frameworks— stateful graphs, tool use, and conditional routing.
- Deep understanding of context engineering andtool / function-callingdesign for reliable agent behavior.
- PracticalRAG experience— embeddings, vector search, and retrieval-quality tuning.
- Fluency withLLM model selection and tuningacross providers, including reasoning models and their trade-offs.
- Experience designingLLM evaluation— offline eval, graders, test sets, metrics, and quality gates.oder
- Comfort withagent observability and tracingto diagnose and improve behavior.
- StrongPythonskills as applied to ML/agent work.
Nice to have
- Experience withagent memorysystems.
- Experience with LangChain suite.
- Experience buildingsafety guardrailsfor high-stakes domains (clinical, financial, legal).
- Experience optimizing LLM latency, cost, and reliabilityat scale.
- E xperience with building and working with MCPs and loop engineering .
- Prompt optimization techniques such as GEPA .
- Working with sensitive data in regulated environmen t.
Transcarent is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees. If you are a person with a disability and require assistance during the application process, please don’t hesitate to reach out!