Senior AI Engineer - LLM Agents
Sign up free to see how well your resume matches this role.
What you'll do
- Design, build, and productionize agentic systems (multi-step reasoning, tool orchestration, guardrails) for materials science search, Q&A and information extraction.
- Develop, integrate and maintain memory systems, MCP servers and agent skills in a multi-agent environment.
- Build evaluation frameworks with domain experts to measure answer quality, extraction accuracy, and retrieval performance.
- Own production reliability & observability of agents you develop.
- Advise adjacent teams on agentic and search system design; flag technical risk and feasibility during roadmap planning.
What they're looking for
- Degree in engineering, computer science, or a quantitative/physical science — or equivalent practical experience.
- 5+ years of software/ML engineering, including 2+ years building LLM-based systems that run in production.
- You have designed evaluations for LLM/agent systems — eval sets, quality metrics, human-expert or LLM-judge pipelines — and can walk us through one (e.g., promptfoo, Braintrust, LangSmith, DeepEval, or your own harness).
- You have instrumented, monitored, and debugged live AI services (e.g., OpenTelemetry, Arize Phoenix, Langfuse, Datadog, or similar).
- Strong Python; able to independently build and deploy services.
Nice to have
- Search/RAG: vector databases, keyword search, knowledge graphs, reranking, hybrid retrieval
- MCP (Model Context Protocol) or agent-tool ecosystem experience
- Materials science, chemistry, or patent/IP domain exposure
- Structured information extraction from technical documents (tables, compositions, specs)
Summarised by NextRaise from the employer’s description, which follows in full below.
Full description from employer
Senior AI Engineer - LLM Agents
Patsnap's Materials team builds AI systems that help R&D scientists and engineers search, extract, and reason over materials science and patent data. You will own the agentic layer of our products end-to-end: LLM-powered agents, tools (MCPs), and the evaluation frameworks that prove they beat general-purpose AI for our customers.
You will be the AI engineer for this team — sole owner of the agentic stack, working directly with product managers, materials domain experts, and our platform team.
Want to see the platform you'd be representing?
Check out this short overview:
This is an in-office position based in our Singapore office.
Who are we?
Patsnap is a global, pre-IPO company that transforms the way organizations harness their Intellectual Property and Research & Development productivity. Our platform revolutionizes how IP and R&D teams collaborate across the entire innovation lifecycle, using domain-specific AI to accelerate the creation of market-ready products. With over 12,000 customers worldwide, including some of the biggest names in innovation, Patsnap is at the forefront of technological advancement. Our $300M Series E funding round brings our valuation to a $1 billion unicorn status, and we still have a remarkable amount of growth ahead.
We have a vibrant and diverse team with offices in Singapore, Toronto, London, Shanghai and remote teams based in US. Our hyper-growth trajectory is powered by our people, and we are extremely proud of our company-wide vision, work ethic, and entrepreneurial spirit. We are committed to fostering an inclusive environment where talent thrives and ideas bloom.
What You'll Be Doing:
Design, build, and productionize agentic systems (multi-step reasoning, tool orchestration, guardrails) for materials science search, Q&A and information extraction.
Develop, integrate and maintain memory systems, MCP servers and agent skills in a multi-agent environment.
Build evaluation frameworks with domain experts to measure answer quality, extraction accuracy, and retrieval performance.
Own production reliability & observability of agents you develop.
Advise adjacent teams on agentic and search system design; flag technical risk and feasibility during roadmap planning.
Why This Role:
Full ownership of a production agent stack that customers pay for
Your evals help decide the roadmap: we build where we can measurably beat frontier general agents
Small senior team, direct access to domain experts and real R&D users
Qualifications:
Degree in engineering, computer science, or a quantitative/physical science — or equivalent practical experience.
5+ years of software/ML engineering, including 2+ years building LLM-based systems that run in production.
You have designed evaluations for LLM/agent systems — eval sets, quality metrics, human-expert or LLM-judge pipelines — and can walk us through one (e.g., promptfoo, Braintrust, LangSmith, DeepEval, or your own harness).
You have instrumented, monitored, and debugged live AI services (e.g., OpenTelemetry, Arize Phoenix, Langfuse, Datadog, or similar).
Strong Python; able to independently build and deploy services.
Nice-to-haves (not required - you’ll have room and support to pick these up on the job:
Search/RAG: vector databases, keyword search, knowledge graphs, reranking, hybrid retrieval
MCP (Model Context Protocol) or agent-tool ecosystem experience
Materials science, chemistry, or patent/IP domain exposure
Structured information extraction from technical documents (tables, compositions, specs)
Company
Company facts come from this company's own listings. We only show what the postings themselves carry.