About the role
About A1
There are over 5 billion users using basic applications today such email, notes, tasks that are not AI-native. Our mission is to build a proactive smart assistant for everyday users to bring intelligence to conversations, errands, organising and workflows, with minimal prompting.
Our product focuses on achieving high reliability for long-running workflows, persistent context, and real-world task completion. The system must handle multi-step reasoning, interact with external tools, and remain reliable despite non-deterministic model behavior. Our objective is to help users complete tasks daily enjoyable with over ~90%* reduced time.
About the Role
As an LLM Application Engineer, you will build the intelligence layer that powers A1's AI experiences.
You will work at the intersection of LLMs, software engineering, and product - designing agent workflows, improving model behaviour, and turning AI capabilities into reliable user experiences.
You will own problems end-to-end, from understanding user needs, designing Agentic workflows, integrating models and tools, building evaluation system and continuously improving AI behaviour in production.
Focus
Build and ship LLM-powered applications and AI agent workflows
Design systems for reasoning, planning, memory, tool uuse and multi-step execution
Build reliable orchestration pipelines that turn probabilistic model outputs into predictable, observable, and safe actions
Integrate LLMs with APIs, databases, search, internal services, and external tools.
Develop prompting, context engineering, structured outputs, tool-calling, and other techniques to improve model behaviour
Build evaluation frameworks and datasets to measure AI quality, reliability, and regressions
Debug AI systems across the entire stack—from model behaviour and prompts to orchestration, backend services, and product UX
Optimise AI systems for quality, latency, and cost
Work closely with product and engineering teams to turn ambiguous product problems into working AI solutions
Establish production practices for observability, tracing, experimentation, evaluation, and continuous improvement
Tech Stack
Python
LLM APIs and model providers, including OpenAI-compatible APIs and open-weight models
Agent frameworks and orchestration systems
Vector databases and retrieval systems
Backend services, APIs, and distributed systems
PyTorch / JAX
Ideal Experience
Strong software engineering fundamentals with experience building AI-powered applications
Hands-on experience with LLMs, generative AI, or agent-based systems
Experience designing prompts, workflows, evaluations, or AI behaviour
Ability to write clean, production-quality code
Comfortable working across abstraction layers (model → system → product)
Strong problem-solving skills in ambiguous, fast-moving environments
Bias toward shipping, iteration, and continuous improvement
Outcomes
AI features reach production quickly and deliver measurable user impact
LLM-powered workflows are reliable, scalable, observable, and maintainable
AI quality improves through systematic evaluation, experimentation, and iteration
AI workflows become increasingly predictable, efficient, and cost-effective
Complex AI capabilities are translated into simple, intuitive user experiences
Originally posted on Himalayas