AI Software Engineer, Agent Harness

Overview

AI Software Engineer focused on building an Agent Harness that runs agents against files and tools while managing permissions, memory, orchestration, and outputs.

What you'll do

• Own the agent harness architecture end to end, including the agent loop, safe execution, context management, memory, permissions, orchestration, outputs, interfaces, and observability.
• Build harness components without equivalent open-source options such as session semantics and enforced permissions.
• Keep the harness updated with changing models via adapters, prompt formats, tool-call schemas, stop conditions, benchmarking, and evaluation.
• Make tool use reliable across models by validating, repairing, retrying, and falling back as needed.
• Develop agents, tools, and MCP servers for internal and customer use cases and review them for security before shipping.
• Build an evaluation harness with task suites and regression runs with cost/latency and quality tracking.
• Define interfaces including a session API, CLI, GUI, and an endpoint existing tools can call.

What you'll need

• 10+ years of software engineering experience in backend systems or ML infrastructure.
• Strong Python and experience with at least one systems language (Go, Rust, or C++).
• Experience shipping and operating an agent loop in production with tool use, multi-step workflows, and unattended runs.
• Hands-on with RAG, context management, and memory for LLM applications.
• Experience with sandboxing, isolation, and permission models for automated systems.
• Understand how quantization and serving choices affect open-weight model behavior.
• Comfort operating in fast-moving, ambiguous environments where you help define the roadmap.

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).
• Observability for LLM systems.
• Document parsing and indexing pipelines.
• Desktop or GUI application experience.

Details

• Location: Bengaluru, Karnataka; or throughout India remote-friendly with travel.