AI Software Engineer, Agent Harness

EnCharge AI · India · Posted Sep 17, 2026


Transparency

Dead

Online for 9 weeks and never reposted. Jobs this old or reposted this often rarely lead to a hire. It may be filled already.

First seen
Oct 10, 2026
Offered for
64 days

Overview

Category
AI & machine learning
Employment type
Permanent
Workplace type
Hybrid
Country
India
Seniority
Senior
Schedule
Full time

Key skills

Agent Harness Architecture
Design and implement end‑to‑end layers for agent loops, context, permissions, and observability.
Backend Systems Programming
Develop high‑performance services in Python and a systems language such as Go, Rust, or C++.
RAG and Memory Management
Build retrieval‑augmented generation pipelines with human‑editable memory and context handling.
Tool‑Calling Reliability
Validate, repair, and retry tool calls, adding fallbacks to ensure consistent execution across models.
Evaluation Harness Development
Create regression task suites, benchmark latency, cost and quality for each model or harness change.
Sandboxing and Permission Models
Implement isolation and permission frameworks to securely run unattended multi‑step workflows.

Key phrases

  • agent loop
  • safe execution
  • context management
  • knowledge base
  • memory
  • permissions
  • orchestration
  • observability
  • session semantics
  • benchmarking and evaluation
  • RAG
  • sandboxing
  • quantization

From the posting

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

More jobs at EnCharge AI

SoC Clocking Specialist (Physical Design)

EnCharge AI · 3 weeks ago | India | On-site · Senior · Full time

Create CV

Power Architect – AI SOC

EnCharge AI · Last month | India | Hybrid · Principal · Full time

Create CV

Senior Marketing Manager - Narrative and Launch

EnCharge AI · Last month | US Remote, Remote - US | $135K–$165K / year | Remote · Senior manager · Full time

Create CV

Staff Physical Design Engineer

EnCharge AI · 2 months ago | US-Remote, Canada, Canada, Remote - US | $170K–$240K / year +1 | Remote · Staff · Full time

Create CV

Technical Program Manager - Embedded Software

EnCharge AI · 3 months ago | US Remote, Remote - US | $200K–$250K / year | Remote · Senior · Full time

Create CV
See all 25 jobs at EnCharge AI