AI Software Engineer, Agent Harness

The role

You will own the harness architecture end to end to run agents against files, tools, documents, memory, and outputs. This involves building components like session semantics, enforced permissions, and orchestrators using open-source and bespoke code.

What you will do

• Own the harness architecture end to end
• Build pieces with no open-source equivalent such as session semantics and enforced permissions
• Keep pace with models including adapters, prompt formats, and tool-call schemas
• Make tool use reliable across models via validation, repair, retries, and fallbacks
• Develop agents, tools, and MCP servers for internal and customer use cases
• Review tools for security before they ship
• Build the evaluation harness including task suites and regression runs
• Define interfaces including session API, CLI, GUI, and endpoints

Required qualifications

• 10+ years of software engineering experience in backend systems or ML infrastructure
• Strong Python and at least one systems language (e.g., Go, Rust, C++)
• Have shipped and operated an agent loop in production
• Hands-on with RAG, context management, and memory for LLM applications
• Experience with sandboxing, isolation, and permission models for automated systems
• Have run open-weight models yourself and understand how quantization and serving choices change model behavior
• Comfort in fast-moving, ambiguous environments where you define the roadmap
• Strong product instincts

Nice to have

• Contributions to open-source agent harnesses or coding agents
• Experience with agent benchmarks (e.g., SWE-bench, Terminal-Bench) and building internal task suites
• MoE serving familiarity e.g. expert placement, tensor parallelism, quantization etc.
• Observability for LLM systems
• Document parsing and indexing pipelines
• Desktop or GUI application experience

About the company

EnCharge AI is building the next generation AI platform with a novel in-memory-computing architecture. The team consists of AI researchers, silicon and systems engineers, and architects.