Member of Technical Staff - Agentic Systems

TL;DR

Context is turning large language models into autonomous coworkers. Our productivity suite lets AI plan reason and execute across 300 business tools. Weve raised $11M (Seed Lux Capital) at a $70M valuation and ship GA this June. Were hiring engineers who live and breathe LLMsbuilding the SDKs runtimes and eval harnesses that make LLM agents reliable at scale.

If you sketch agent flows in Excalidraw obsess over tokenlevel traces etc. lets talk.

Why build agents at Context

• Impact: Frontier playground

• 50Mtoken memory agents with persistent cognition well beyond frontier models.

• Fullstack autonomy: Agents open docs write slides hit APIs and replanno brittle RPA hacks.

• Tight feedback loops: Beta fleet drives >5K agent runs/day; your PRs hit prod within hours.

• Elite peers: Microsoft Research Stanford Tesla peerszero bureaucracy.

• Hardware ally: Qualcomm SnapdragonXElite partnership: 10 lower latency ondevice privacy. Gateway into enterprise & government.

What youll build

• Agent SDK (TypeScript) a composable toolkit (task graph tools memory adapters) powering both serverside and edge runtimes.

• Swarm Runtime orchestrator in that schedules supervises and retries agent subtasks at millisecond granularity.

• Graph Traversal APIs ergonomic wrappers around our 50Mtoken knowledge graph with streaming partial updates and vector fallbacks.

• Adaptive Prompt Compiler realtime TS library that compiles structured inputs modelspecific prompts and parses responses.

• Evaluation Harness Jest/Playwrightstyle test runner that autoredteams agents for hallucinations tooluse failure and latency regressions.

Tech youll touch

TypeScript (18) Bun Cloudflare Workers / V8 isolate
LangChainJS LlamaIndex TS custom lightweight frameworks
OpenAI Anthropic Llama CPP bindings
Rust (via NAPI) for hot paths WebGPU/WebAssembly for clientside reasoning
Postgres Redis Apache Arrow bespoke graph store
Kubernetes GCP Edge functions

You might be a fit if

• Youve shipped production TS/Node services at scale and love typelevel safety.

• Youve built or contributed to agent / retrieval frameworks (LangChainJS AutoGen custom) and can dissect their failure modes.

• You treat prompts as code: unittest them version them and lint them.

• Comfortable jumping into Rust/Wasm when the profiler says so.

• You think debuggers trace viewers and livereload matter as much as model choice.

Bonus points

• Authored OSS in the LLM tooling ecosystem (LangChainJS plugin OpenAI helper lib etc.).

• Experience with CRDT/OT for collaborative agent state or liveshare UIs.

• Prior work on distributed schedulers or graph databases.

Compensation & Perks

• Topofband salary founderlevel equity

• Medical dental vision 401(k) match

• Custom rig & conference budget

• Biannual team offsites (Tahoe powder NYC AI Week etc.)

Ready to push LLMs beyond chatwith TypeScript

Email with a short intro and links (repos demos papers). We reply within 48 hours.

Required Experience:

Staff IC