Senior Software Engineer, AI Agents

About Asha Health

Asha Health helps medical practices launch their own AI clinics. We're backed by Y Combinator, General Catalyst, 186 Ventures, Reach Capital and many more. We recently raised an oversubscribed seed round from some of the best investors in Silicon Valley. Our team includes AI product leaders from companies like Google, physician executives from major health systems, and more.

About the Role

We're looking for a top 0.01% Software Engineer to join our engineering team in our Bangalore office.

4.6 fundamentally changed the game, which means that high intelligence, high agency engineers can now do the work of 10+ good engineers. It doesn't make sense to have anyone but the best on the team.

Since low level coding has become easier, what we expect from engineers on our team has expanded. Engineers on our team are expected to:

• Ship features end to end at a rapid pace
• Deeply research the domain and be their own product managers
• Ensure reliability and quality is best-in-class
• Design robust eng architecture, and develop testing and observability tools for each feature pre-launch
• Build each feature with deep customer empathy, meaning planning out and building stellar UX yourself

This means to thrive in a startup environment like ours, you not only need to be a stellar engineer, but you need to:

1. Be super adept with AI development tools and building the AI systems that build your features for you (Conductor, Browser agents, QA agents, Ralph loops, adverserial agents, and more).
2. Have exceptional product and UX taste, meaning you can ship features that are more effective than those historically designed by teams of product managers and designers.
3. Take the highest level of ownership around feature outcomes, reliability, and observability.

Other Points to Note

1. We are growing rapidly, our work has impact on tens of thousands of patients if not more.
2. On our team, everything you do is on the bleeding edge of applied AI.
3. We expect a high level of commitment from everyone on the team, most folks work 6 days and lead every project with intensity. It's a high ask, and we only bring on the best people. We compensate significantly above market, accordingly.

About the Role

We are looking for a senior backend engineer to build the infrastructure that powers AI agents in enterprise environments. You will work on systems that securely run, manage, monitor, and govern AI agents as they interact with users, business applications, and external tools.

This role combines backend engineering, distributed systems, AI agent infrastructure, security, and platform development.

Responsibilities

• Build and maintain the core runtime that manages AI agent execution and lifecycle.
• Develop systems for message processing, task orchestration, queue management, and recovery from failures.
• Design secure communication and execution boundaries between AI agents and the host platform.
• Build and enhance sandboxed environments for safe tool and code execution.
• Develop scalable backend services, APIs, and platform components.
• Build admin interfaces and APIs for configuring agents, permissions, approvals, and audits.
• Implement capability, access control, and permission management systems.
• Develop durable memory and state management systems for AI agents.
• Build integrations with communication platforms, business applications, and external systems.
• Improve platform reliability, observability, security, and performance.
• Collaborate closely with engineering teams to design, develop, test, and ship new capabilities.

Required Skills & Experience

• 5+ years of backend software engineering experience.
• Strong proficiency in TypeScript, Node.js, or another modern typed programming language.
• Experience building scalable, distributed, and event-driven systems.
• Strong understanding of databases, transactions, queues, background workers, and system reliability.
• Experience designing and building REST APIs and backend services.
• Hands-on experience using AI coding tools and assistants in daily development workflows.
• Understanding of AI agent frameworks, agent workflows, tool calling, context management, or agent orchestration concepts.
• Strong knowledge of system design, security principles, authentication, authorization, and access control.
• Experience debugging, optimizing, and maintaining production systems.
• Ability to work independently in large codebases and deliver high-quality solutions.

Good to Have

• Experience with AI agent frameworks or SDKs.
• Experience building developer platforms, admin consoles, or management systems.
• Knowledge of sandboxing, process isolation, containers, or secure execution environments.
• Experience with distributed systems concepts such as ordering, retries, idempotency, and fault recovery.
• Experience designing extensible architectures and integration platforms.
• Exposure to AI infrastructure, LLM applications, or autonomous agent systems.

What We're Looking For

• Strong backend engineering fundamentals.
• Security-first mindset.
• Experience building reliable production systems.
• Interest in AI agents and AI infrastructure.
• Ability to move quickly, solve complex technical problems, and work in a fast-paced environment.

Experience: 5+ years production software engineering, with 2+ years working directly on LLM or agent systems in production. 

Location: Remote 

To streamline and fast-track screening, please submit your details here (if you haven’t already): https://airtable.com/appbtkr4odapnb5I6/pagqo91lKv3VJg3GT/form 

We’ll review your responses as part of the initial screening process. Please make sure you complete and submit all details through the form to be considered for the next stage. Submissions outside the form may not be considered.

Why This Role Matters

Terrabase builds agent infrastructure that enterprise customers rely on daily for SQL generation, forecasting, data analysis, and artifact delivery. Our orchestration layer routes between specialized sub-agents, manages typed handoff contracts, runs structured eval suites, and enforces correctness across every turn.

This is not a research-prototype role. You will build and evolve agent architecture, but always in service of making the system observable, typed, evaluated, recoverable, and boringly reliable in production.

What You Will Do

Own the harness architecture and middleware stack. Our LangGraph orchestrator routes between sub-agents through a layered middleware stack: file upload handling, source resolution, local context, workspace sync, state hydration, aggregation barriers, and typed handoff contracts. You will extend this stack, enforce its contracts in code, and keep it operational as routing logic and agent surfaces evolve.

Maintain typed contracts and boundaries. Agent handoffs at Terrabase carry typed contracts with barrier conditions and retry predicates. You will design these contracts, enforce them with strict typing, manage backward compatibility when contracts change, and write the contract tests that prevent silent regressions.

Own the eval suites. We run structured eval suites across routing decisions, context-resolution accuracy, multi-turn coherence, visual reference alignment, and artifact correctness. You will extend coverage, write new evals where gaps exist, and build CI gates that block releases when regressions are detected. A routing change or prompt change with no eval coverage does not ship.

Triage production failures and close the loop. When an agent turn fails in production, you will trace it in LangSmith, identify the failure class, and convert it into a durable regression test. You will own the release gates, keep prompts and runtime contracts in sync, manage feature flag rollout risk, and remove dead paths as the system evolves.

Own SQL and artifact correctness. Our agents generate SQL over customer schemas and produce structured artifacts (reports, dashboards, data sheets) under a strict schema contract. You will own the correctness layer: source grounding, schema-aware validation, provenance surfaces, and the eval infrastructure that catches generated artifact failures before they reach customers.

Build and maintain HITL workflows. Human-in-the-loop checkpoints let users intervene, redirect, or approve mid-chain. You will design these workflows, enforce their resumable state contracts, and ensure they degrade gracefully when interrupted.

Instrument for traceability. You will extend LangSmith tracing coverage, add structured span annotations, and build the tooling that lets us diagnose a bad agent turn from production trace data alone, without requiring a local reproduction.

What We Are Looking For

• 5+ years production software engineering, with strong Python fundamentals
• 2+ years working hands-on with LLM-based systems: agent loops, tool use, context management, or inference pipelines
• Experience with LangGraph, LangChain, OpenAI/Anthropic tool-use systems, or equivalent multi-step agent/runtime orchestration
• Practical eval engineering: you have built or extended eval harnesses, written automated test cases for agent behavior, and treated evaluation as an ongoing engineering discipline
• Strong engineering hygiene: strict typing, small interfaces, contract tests, clear schema migrations, and CI discipline
• Ability to debug from production traces and artifacts, not only local reproductions
• Comfort working across prompts, Python runtime code, TypeScript product surfaces, data systems, and eval infrastructure
• Systems thinking: you design for observability, recovery, and state management, not just the happy path
• Maintenance ownership mindset: you triage, close loops, and leave systems more debuggable than you found them
• Pragmatic judgment: you can distinguish between reliability-critical infrastructure and speculative abstraction

Bonus Points

• HITL workflow design: checkpoints, approvals, mid-chain interrupts, resumable state
• Context engineering depth: chunking strategies, retrieval-augmented generation, semantic routing, re-ranking
• Experience with LangSmith, Weights and Biases, or similar trace and evaluation platforms
• Prior work shipping agent systems to enterprise customers where SQL or data correctness is a hard requirement
• Experience with mypy, Pydantic contracts, or strict typing disciplines in a production Python codebase

Life at Terrabase

We are a sharp, focused, fully remote team building agent infrastructure that enterprise customers trust with their data. You will work directly alongside the engineer who designed this harness, with broad ownership, generous compute budgets, and a culture that treats reliability as a product requirement, not a research topic.

Terrabase is an equal-opportunity employer. We celebrate diversity and are committed to building an inclusive environment for every team member.

Who we are: My AI Client is building the foundational platform for the "agentic economy," moving beyond simple chatbots to create an ecosystem for autonomous AI agents and they aim to provide tools for developers to launch, manage, and monetize AI agents as "digital coworkers."

The Challenge

The current AI stack is fragmented, leading to issues with multimodal data, silent webhook failures, unpredictable token usage, and nascent agent-to-agent collaboration. My AI Client is building a unified, robust backend to resolve these issues for the developer community.

Your Mission

As a foundational member of the backend team, you will architect core systems, focusing on:

• Agent Nervous System: Designing agent-to-agent messaging, lifecycle management, and high-concurrency, low-latency communication.
• Multimodal Chaos Taming: Engineering systems to process and understand real-time images, audio, video, and text.
• Bulletproof Systems: Developing secure, observable webhook systems with robust billing, metering, and real-time payment pipelines.

What You'll Bring

• My AI Client seeks an experienced engineer comfortable with complex systems and ambiguity.

Core Experience:

● Typically 3 to 5 years of experience in backend engineering roles.

● Expertise in Python, especially with async frameworks like FastAPI.

● Strong command of Docker and cloud deployment (AWS, Cloud Run, or similar).

● Proven experience designing and building microservice or agent-based architectures.

Specialized Experience (Ideal):

• Real-Time Systems: Experience with real-time media transmission like WebRTC, WebSockets and ways to process them.
• Scalable Systems: Experience in building scalable, fault-tolerant systems with a strong understanding of observability, monitoring, and alerting best practices.
• Reliable Webhooks: Knowledge of scalable webhook infrastructure with retry logic, backoffs, and security.
• Data Processing: Experience with multimodal data (e.g., OCR, audio transcription, video chunking with FFmpeg/OpenCV).
• Payments & Metering: Familiarity with usage-based billing systems or token-based ledgers.

Your Impact

• The systems designed by this role will form the foundation for:
• Thousands of AI agents for major partners across chat, video, and APIs.
• A new creator economy enabling developers to earn revenue through agents.
• The overall speed, security, and scalability of my client’s AI platform.

Why Join Us?

• Opportunity to solve hard problems with clean, scalable code.
• Small, fast-paced team with high ownership and zero micromanagement.
• Belief in platform engineering as a craft and care for developer experience.
• Conviction that AI agents are the future, and a desire to build their powering platform.
• Dynamic, collaborative in-office work environment in Bengaluru in a Hybrid setup (weekly 2 days from office)
• Meaningful equity in a growing, well-backed company.
• Direct work with founders and engineers from top AI companies.
• A real voice in architectural and product decisions.
• Opportunity to solve cutting-edge problems with no legacy code.

Ready to Build the Future?

My AI Client is building the core platform for the next software paradigm. Interested candidates are encouraged to apply with their GitHub, resume, or anything that showcases their thinking.

Company Description

Recruiting Bond International is a next-generation Talent Intelligence, Executive Search, and Human Capital Advisory firm helping start-ups, enterprises, GCCs, and VC/PE-backed companies build high-impact global teams. It is a global leader in Recruitment Process Outsourcing (RPO), executive search, and workforce consulting, specializing in building transformative talent strategies.

From high-growth startups to Fortune 500 companies, Recruiting Bond partners with organizations across 50+ industries and 140+ countries to deliver fast, scalable, and inclusive hiring solutions. The company supports businesses in scaling teams, fostering innovation, and creating talent-first strategies to achieve their goals.

With deep expertise across Technology, FinTech, Healthcare, Real Estate, and Energy, Recruiting Bond is dedicated to building careers, companies, and futures by connecting world-class talent with high-impact opportunities globally.

About the Role

Our client is hiring a Backend Engineer (India-based, Remote) to design, build, and scale the core memory infrastructure powering production-grade AI agents.

This role is intended for an experienced engineer with 7–10 years of backend engineering experience, who has deeply internalized AI-native engineering practices and actively builds using tools such as Claude Code, Codex, Cursor, Windsurf, or comparable AI development tools as a core part of their workflow.

The hiring process is intentionally non-traditional and skill-first. There is no evaluation based on IIT pedigree, LeetCode performance, or conventional resume filters. Instead, the only evaluation criterion is: how you build with AI in real-world scenarios.

Candidates are expected to submit prompt logs or transcripts from Claude Code, Codex, Cursor, or Windsurf demonstrating a feature or product they are proud of.

What You'll Own

• Build and scale backend systems powering the memory infrastructure of the product
• Own and deliver features end-to-end, integrating AI coding tools into the core development workflow
• Design, manage, and optimize database, storage, and retrieval systems for persistent memory
• Collaborate closely on system architecture, scalability, performance, and reliability engineering
• Contribute directly to product roadmap decisions based on real customer usage and production insights

Requirements

Must-Have

• 7–10 years of backend engineering experience
• Demonstrated ability to build with AI coding tools (Claude Code, Codex, Cursor, Windsurf, or comparable)
• Ability and willingness to submit prompt log transcripts from a feature or product you are proud of
• Strong Python fundamentals
• Strong PostgreSQL or comparable relational database fundamentals
• Comfort owning systems end-to-end in production
• Based in India, remote work from anywhere in the country

Nice-to-Have

• Prior AI infrastructure or developer tools product experience
• FastAPI fluency
• Open-source contributions in AI, memory, vector databases, or developer tools
• Prior experience in memory systems, RAG pipelines, or vector database engineering
• Public technical writing or conference talks on AI-native engineering practices

AI Engineer — Vertexcover Labs

Who We Are

Vertexcover Labs is an employee-focused, engineer-run software studio. We partner with fast-growing, funded startups around the world—Rephrase.ai, Dhiwise, Dunzo, Dubdub, Xapo, Arintra etc.—to crack their toughest engineering problems. Everyone is an individual contributor; no management layers. Engineers choose the projects they work on, see each project's P&L, and share directly in the profits.

Whether it's building multi-agent systems for production, scaling ML pipelines across GPU clusters, or shipping RAG-powered products that end-users rely on—we solve hard AI problems for real companies.

A Few Problems We Are Currently Working On

• AI Agents Test-authoring agents that convert natural language into e2e tests.
• Ad-performance agents that learn what works for your brand and generate winning creatives automatically.
• Scale + MLOps Optimise ML pipelines and fix autoscaling by applying queuing theory while juggling CPU / GPU memory contention.
• RAG & Knowledge Systems Design and deploy retrieval-augmented generation pipelines—chunking strategies, embedding models, reranking, and evaluation loops.
• AI Video & Image Processing Build rendering pipelines, diffusion-model integrations, and real-time video processing at scale. You'll own at least one project like these—design, build, iterate.

Signals You're Probably the Right Fit

• Strong in at least one other language (Python, Go, Rust, TypeScript, Java …); happy to learn more.
• First principle understanding of how LLMs, embeddings, vector databases and AI Agents work
• Evidence of shipping real AI-powered software—OSS, side projects, or production features.
• Comfortable navigating the fast-moving AI landscape—papers, new model releases, evolving APIs.
• Clear written & spoken communication; async collaboration is our default.
• Self-directed—you ask for context, not permission.

How We Operate

• Project choice. Engineers vote on which engagements we take.
• Stack agnostic. We pick tools that fit the job, not the résumé.
• Pragmatic craftsmanship. Durable design, no gold-plating.
• Transparent economics. Know what your work is worth, share in the profits.
• Remote-native. Async by default; sync when it helps.

Hiring Process (Lean & Human)

1. 2–3 technical deep-dives with future teammates.
2. 30-minute culture chat.
3. Offer. No LeetCode marathons, no trick puzzles.

We read every application and reply to all candidates.

Senior BackEnd Engineer

The ideal candidate will have a strong background in building scalable applications, a deep understanding of back-end technologies, and experience with cloud infrastructure. As a Back End Engineer, you will be responsible for designing, developing, and maintaining a scalable workflow management system. You will work closely with cross-functional teams to build robust and efficient applications that meet the needs of our users. Your expertise in Scala, Python, AI Agents/APIs, and GCP will be crucial in ensuring our system is reliable, performant, and scalable.

Key Responsibilities:

Back-End Development:

• Build and maintain back-end services and APIs using Scala.
• Implement and optimize Orchestration workflow system involving database queries and operations.
• Build API integrations with Third Party APIs and services.
• Ensure robust and scalable server-side logic.

Cloud Integration:

• Deploy, manage, and monitor applications on Google Cloud Platform (GCP).
• Utilize GCP services to enhance application performance and scalability.
• Implement cloud-based solutions for data storage, processing, and analytics.

Collaboration And Communication:

• Work closely with cross-functional teams to define, design, and ship new features.
• Participate in code reviews and contribute to sharing team knowledge.
• Document development processes, coding standards, and project requirements.

Qualifications:

• Educational Background:
• Completed a masters/bachelor degree in Computer Science, Engineering, or a related field.
• Technical Skills:
• Proficiency in Scala programming language.
• Strong experience with React and ReactJS.
• Familiarity with Google Cloud Platform (GCP) and its services.
• Knowledge of front-end development tools and best practices.
• Understanding of RESTful API design and implementation.
• Soft Skills:
• Excellent problem-solving skills and attention to detail.
• Strong communication and collaboration abilities.
• Eagerness to learn and adapt to new technologies and challenges.

Preferred Qualifications:

• Experience with version control systems such as Git.
• Familiarity with CI/CD pipelines and DevOps practices.
• Understanding of workflow management systems and their requirements.
• Experience with containerization technologies like Docker.

Must have Skills

• Scala - 4 Years
• React.Js - 1 Years
• RESTful API - 4 Years
• Docker - 2 Years
• Python - 3 Years
• Artificial Intelligence - 2 Years