AI Software Engineer, Agent Harness
Free to start · No card · 5 credits the moment you sign up
Job description
AI Software Engineer, Agent Harness
Location: Bengaluru, Karnataka (or throughout India remote-friendly with travel)
About EnCharge AI
EnCharge AI is building the next generation AI platform. Our novel in-memory-computing architecture delivers a 10x step-function improvement in compute energy efficiency and performance for AI inference workloads. As the demands of artificial intelligence move beyond today's models, we believe fundamental underlying infrastructure must evolve. We are an experienced team of AI researchers, silicon & systems engineers, and architects backed by leading investors, poised to become the essential platform for the next wave of AI innovation.
The Opportunity
We serve open-weight models and our own bespoke checkpoints on EnCharge hardware. The models change often, and the harness around them needs to keep up. You own this layer that runs agents against files, tools, documents with permissions, memory, unattended execution, and real outputs. It will be assembled from a combination of open-source and bespoke code.
Key Responsibilities
- Own the harness architecture end to end — agent loop, safe execution, context management, knowledge base, memory, permissions, orchestration, outputs, interfaces, observability — one component per layer, with clear interfaces so layers can be swapped.
- Build the pieces with no open-source equivalent e.g. session semantics, enforced permissions, memory in a human-editable file, orchestrator, and outputs.
- Keep pace with the models: adapters, prompt formats, tool-call schemas, stop conditions, benchmarking and evaluation.
- Make tool use reliable across models of uneven tool-calling quality — validation, repair, retries, fallbacks.
- Develop agents, tools, and MCP servers for internal and customer use cases, and review them for security before they ship.
- Build the evaluation harness: task suites, regression runs on every model or harness change, cost and latency per task alongside quality.
- Define the interfaces: session API, CLI, GUI, and an endpoint existing tools can point at.
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 — tool use, multi-step workflows, unattended runs
- 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
Originally posted on Himalayas
Prepare your application
Use the description above to assess your fit for EnCharge AI. This checklist is guidance from Resumize, rather than additional requirements from the employer. Imported listings can be shortened or change after collection, so confirm the complete description and current availability before sending an application.
Match requirements to evidence
Identify the responsibilities and skills the employer explicitly names. For each important requirement, choose one example from your work, education, training, or projects. Explain what you did, how you did it, and what changed as a result. Include a measurable outcome when you can support it. If you lack a requirement, describe related experience accurately instead of adding an unfamiliar skill to your resume.
Put the most relevant examples near the top of your resume. Keep job titles, dates, qualifications, and contact details consistent across your application materials. Use the employer’s terminology when it describes your experience accurately; a copied list of keywords does not explain your contribution. A short, specific bullet is easier to review than a paragraph that mixes several unrelated duties.
Check the working arrangement
Confirm the location, schedule, employment type, and any eligibility requirements on the employer’s site. A remote label does not establish worldwide eligibility or flexible hours. If compensation, benefits, equipment, travel, or contract duration are missing from this listing, write down your questions for the recruiter. Do not assume details from another opening at the same company apply to this role.
Review before submitting
Follow the employer’s requested file format and application instructions. Open your exported resume and check that its text is selectable, its sections read in order, and its links work. Proofread names, dates, and contact information. Share confidential work samples only when you have permission, and use an anonymized example when necessary.
Submit through a trusted employer or recruiting destination. If the original listing has disappeared, search the employer’s careers page for the title rather than assuming the vacancy remains open. Save the application date, job reference, and the version of your resume you sent. Those details help you prepare for a later conversation and avoid submitting conflicting information through several job boards.
Review your resume for writing and readability feedback, or browse other openings if this opportunity is unavailable.