Agent Engineer

About the role

We are building an AI‑native B2B intelligence platform and need a hands‑on Engineer to create the core “Agentic Harness”. The harness will power everything from database search to autonomous sourcing and selling agents, and must be performant, configurable and model‑agnostic.

Key responsibilities

• Design and implement a lightweight, scalable agent harness that can be configured and deployed for multiple domain‑specific agents.
• Build the orchestration loop, handling memory management, state, tool calling and deterministic guardrails.
• Ensure the layer works with both commercial and open‑source large language models, allowing easy model swapping and testing.
• Optimize agent latency, token usage and memory footprint through benchmarking and profiling.
• Develop robust evaluation frameworks to measure reasoning, tool‑selection accuracy and task completion.
• Collaborate with the research team to fine‑tune open‑source models for optimal agentic behavior.

Required profile

• 3–6 years of experience in backend or machine‑learning engineering.
• Strong systems‑engineering mindset with a focus on reliable software development rather than prompt engineering.
• Proven ability to design and maintain complex orchestration workflows.

Required skills

• Python programming.
• FastAPI for building APIs.
• PostgreSQL database integration.
• Experience with large language model (LLM) application architecture and state‑machine design.
• Benchmarking, profiling and performance optimisation of LLM‑driven systems.