SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Form Energy is building the internal AI platform that enables teams across the company to create and deploy AI-powered applications safely and quickly. As a Staff AI Platform Engineer, you will be a hands-on senior individual contributor designing and operating the shared infrastructure that other engineers depend on—including application runtime, knowledge systems, agent infrastructure, and governance tooling.
Your responsibilities span:
• Building and operating an internal application platform where employees can create and deploy AI applications with pre-built frameworks, templates, authentication, and secure deployment, so teams focus on business logic and UX.
• Providing governed data access to applications, including connectivity to the data warehouse and a shared Postgres cluster, automatically integrated into the data platform.
• Designing and operating a central knowledge platform over unstructured content (documents, transcripts, Slack) and structured data from battery test stands, manufacturing robots, and deployed systems. You will own retrieval quality through semantic and hybrid search, re-ranking, chunking, and classification, with source-level permissions and evaluation sets.
• Designing and deploying shared Model Context Protocol (MCP) infrastructure, including gateway layers for authentication, authorization, rate limiting, and audit logging, and building MCP servers across the software organization.
• Owning model selection and cost optimization: evaluating open-source and frontier models on internal tasks, deciding where each fits, and reducing token usage through context management, caching, and model routing.
• Building the agent orchestration layer, including multi-agent workflows, long-running loops with checkpoints, human review gates, and automated evaluation. Collaborating with data engineers to determine when work should run as deterministic workflows versus agent-driven state machines.
• Partnering with product R&D, battery design, manufacturing, and root cause analysis teams to identify and automate repeatable work, including agent workflows that inform critical design and process decisions.
• Instrumenting the platform with tracing, evaluation, usage, and cost attribution by team. Standing up AWS infrastructure and infrastructure-as-code (Pulumi and/or Terraform).
• Establishing a company-wide skills and plugin marketplace that vets contributions against AI policy and scans for security vulnerabilities. Advising on AI governance and automating policy execution.
• Raising the engineering bar through design docs, RFCs, code review, mentorship, and technical influence beyond the immediate team.
Form Energy is a climate-tech company revolutionizing energy storage with cost-effective, multi-day iron-air battery systems. The company has been recognized by TIME, MIT Technology Review, and Fast Company, and is scaling manufacturing at its West Virginia facility while signing contracts with leading US utilities.
This is a hybrid role requiring 3+ days per week onsite from Somerville, MA; Berkeley, CA; or Weirton, WV. Relocation assistance is available.
**REQUIREMENTS:**
• Bachelor's degree in computer science, software engineering, computer engineering, or related field, plus 7+ years of software or data engineering experience, including building and operating production platforms or services that other engineers depend on.
• Strong production programming in Python and Go, with experience building APIs and backend services.
• Hands-on experience building LLM-powered systems in production, including retrieval-augmented generation, embeddings, vector and hybrid search, re-ranking, and structured-data access through text-to-SQL or semantic layers.
• Experience with agent frameworks, tool calling, and the Model Context Protocol, and with workflow orchestration or state-machine frameworks such as LangGraph, Temporal, or Dagster.
• Experience building evaluation sets and harnesses for LLM systems and measuring quality, latency, and cost across model providers, including open-weight models.
• Experience with PostgreSQL and a cloud data warehouse, plus AWS, containers, CI/CD, and infrastructure-as-code with Pulumi and/or Terraform.
• Working knowledge of platform and AI security: authentication and authorization (OAuth/OIDC), secrets management, sandboxed execution, tenant isolation, supply-chain scanning, and risks specific to LLM tools such as prompt injection and data exfiltration.
• Track record of building internal platforms that other teams adopt, and of independently leading the design of novel solutions through technical design docs and RFCs.
• Excellent communication and organizational skills, including with scientists, engineers, and operators who aren't software developers, and comfort participating in an on-call rotation.
• Nice to have: React and design-system experience; Snowflake or Databricks; serving open-weight models (e.g., vLLM); API or AI gateway experience; AI governance or compliance frameworks (SOC 2, ISO 27001); background in battery, energy, manufacturing, or physical-systems data.
