AI Software Engineer, Agent Harness
EnCharge AI (company site, opens in a new tab)10+ yrsOn-siteDirect career pageEst. 45–75 LPA
Posted on 16 Sept
Reach people at EnCharge AI
People at this company you can reach
Log in to see who works here
Create a free account or log in to see the people at EnCharge AI you could write to:
- Recruiters & HR
- People in this function
- Work addresses
Your match
Against your primary resume
Log in to see your match score
Create a free account or log in to unlock your CV match score across:
- Role fit
- Experience
- Industry relevance
Protocol Intelligence
How competitive this role is
Competition
Background fit
Strictness
Log in to see why each signal reads the way it does.
Job description
Structured overview of role & requirements
About This Role
- Own and develop the entire agent harness architecture responsible for running AI agents on files, tools, and documents with managed permissions, memory, and execution orchestration.
- Build unique components such as session semantics, enforced permissions, memory management, orchestrators, and outputs not available in open-source alternatives.
- Maintain compatibility with evolving AI models including adapters, prompt formats, tool-call schemas and build robust validation, retries, and fallback mechanisms for tool usage.
Minimum Requirements
- 10+ years of software engineering experience in backend systems or ML infrastructure.
- Proficient in Python and at least one systems programming language (Go, Rust, C++).
- Experience shipping and operating production agent loops involving tool use, multi-step workflows, and unattended runs.
- Experience with retrieval-augmented generation (RAG), context management, sandboxing, isolation, and permission models; experience running open-weight AI models and familiarity with quantization and serving impacts.
Ideal Candidate Profile
- Experienced in developing complex AI agent orchestration systems with a strong emphasis on backend architecture and security.
- Comfortable defining technical roadmaps and product direction in ambiguous and fast-paced environments.
- Familiar with evaluation harnesses, benchmarking, and building resilient AI tooling that supports varied AI model behaviors and multi-modal workflows.