Senior Platform Engineer (Core Platform) for Concourse

TurnKey Labs; New York (NY); On-site; USD 150,000 - 230,000; Full time

Benefits offered by this job

Flexible PTO

Fully remote

Personal laptop

Health and wellness package

Job summary

TurnKey Labs seeks a senior backend/platform engineer to design and own the AI orchestration backend, enabling long-running agent pipelines across tasks and engagements.

You will build shared services, SDKs, and tools, set reliability and security standards, and guide build-vs-buy decisions while collaborating with forward-deployed teams to ship at startup pace.

Qualifications

• 4+ years of backend/platform engineering experience.
• Fluency in Python and/or TypeScript/Node.
• Experience with long-running workflows and job queues.
• Hands-on experience building or operating LLM/agent infrastructure.
• Proficient in English for async collaboration.
• Available for ~4 hours of overlap with US Eastern Time.

Responsibilities

• Design and own the AI orchestration backend — the engine that runs long, back-to-back agent pipelines reliably across tasks, users, and engagements (queues, retries, state, observability, cost)
• Build the shared services every engagement plugs into: auth, data model, file ingestion, internal APIs, vector / RAG infrastructure, eval pipelines
• Provide a clean developer surface (SDK, CLI, internal libraries) so engagement teams can stand up a new client workflow in hours, not days
• Set the bar for reliability, security, and cost-efficiency across the platform — this is software that powers government deliveries, not toys
• Make the right build-vs-buy calls on infrastructure (model gateways, vector stores, queues, observability)
• Pair with forward-deployed teams to spot recurring patterns and lift them into the platform
• Use AI coding tools (Claude Code, Cursor, etc.) aggressively to ship at startup pace with senior-engineer judgment

Skills

Backend engineering

Python

TypeScript/Node

LLM infrastructure

AI coding tools

English proficiency

Tools

LangGraph

Custom agent loops

Job description

Full-time · Remote (Offshore) · ~4 hours/day overlap with US Eastern Time

Design, build, and own the core platform that powers every Concourse engagement — the orchestration engine, shared services, and developer surface our forward-deployed teams build on.

About The Product

Concourse is an early-stage, fast-growing startup building AI-powered software for state and local governments. This is the CEO’s second venture after a successful exit.We sell technology to state and local governments, aiming to improve public services by replacing legacy, inefficient systems. The core problem we address is the disconnect between tax payments and perceived government inefficiency — often due to outdated technology.We’re building an AI-native company where every team member is empowered to use AI tools like Claude to automate their work. Our team has a hub in Flatiron, NYC, and we support remote roles where it fits the role.

Why This Role

Own the Engine You’re not embedded in a single client — you build the platform the entire company depends on. Every FDE and engineer on the team uses what you ship.

Real Leverage A pattern you introduce — a better agent runtime, cleaner SDK, faster eval loop — compounds across every engagement we run.

Senior Seat from Day One Strong technical opinions are wanted, not tolerated. You set standards across the platform.

Frontier AI Infrastructure You’ll be designing the kind of systems most teams haven’t built yet: long-running agent pipelines, multi-step workflows with human-in-the-loop, cross-engagement context, evals.

What You’ll Do

• Design and own the AI orchestration backend — the engine that runs long, back-to-back agent pipelines reliably across tasks, users, and engagements (queues, retries, state, observability, cost)
• Build the shared services every engagement plugs into: auth, data model, file ingestion, internal APIs, vector / RAG infrastructure, eval pipelines
• Provide a clean developer surface (SDK, CLI, internal libraries) so engagement teams can stand up a new client workflow in hours, not days
• Set the bar for reliability, security, and cost-efficiency across the platform — this is software that powers government deliveries, not toys
• Make the right build-vs-buy calls on infrastructure (model gateways, vector stores, queues, observability)
• Pair with forward-deployed teams to spot recurring patterns and lift them into the platform
• Use AI coding tools (Claude Code, Cursor, etc.) aggressively to ship at startup pace with senior-engineer judgment

What We\'re Looking For

• 4+ years of backend / platform engineering experience, with meaningful time on systems that other engineers built on top of (internal platforms, SDKs, orchestration layers, devtools)
• Deep fluency in Python and/or TypeScript/Node, and comfort dropping into a React frontend when the platform needs a control surface
• Experience designing systems with non-trivial state and long-running workflows — job queues, retries, idempotency, observability, backpressure
• Hands-on experience building or operating LLM / agent infrastructure: orchestration loops, tool use, RAG pipelines, evals, prompt/version management, cost tracking
• Daily, fluent use of AI coding tools (Claude Code, Cursor, Codex, etc.) — you’ve absorbed them into how you build, not just tried them
• Strong product instincts: you make the platform serve the team’s velocity, not the other way around
• Clear spoken and written English and the ability to lead technical conversations async with a US-based team
• Available for ~4 hours of daily overlap with US Eastern Time (roughly 9am–1pm ET)

Nice to Have

• Built or scaled an internal platform at an early- or growth-stage startup
• DevOps / SRE experience — cloud infra (AWS/GCP), IaC, CI/CD, monitoring, security hardening
• Experience with agent frameworks (LangGraph, custom loops) and an opinion about what they get wrong
• Familiarity with regulated / public sector environments (SOC 2, FedRAMP-adjacent, gov cloud)
• Open-source contributions or technical writing that show how you think

We offer

• We welcome new ideas and allow you to make an immediate impact on the team.
• Flexible Paid time off (PTO for any reason, including sick days (no specified limits) and flexible work schedule).
• Personal laptop.
• Health and wellness package.
• Fully remote.

As this is an English-speaking role, we kindly ask that all applications be submitted with a CV in English.