SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Neara is building AI-powered digital twins of electricity grids across four continents using advanced machine learning and physics-enabled simulation. The company helps utilities understand infrastructure challenges, optimize investments, and build resilient energy systems by simulating extreme weather and structural stress at network-wide scale.
As an AI Product Engineer, you will be one of the first members of a new team shipping LLM and agentic features into a product that utilities use to make critical infrastructure decisions. Your focus is the product layer—LLMs, agents, retrieval, and tool use—grounded in Neara's digital twin, physics engine, and network data that customers already trust.
Key responsibilities:
- Design, prototype, and ship AI-powered features end-to-end from problem identification through production deployment
- Build agentic and retrieval-based systems grounded in the digital twin and simulation outputs, ensuring every answer traces back to its source model
- Own the critical challenge of making AI output trustworthy in a domain where incorrect answers about clearance or pole loading are safety problems, not UX issues. Design guardrails, refusals, confidence signals, and human-in-the-loop checkpoints
- Build evaluation discipline: eval sets, regression testing, offline/online quality signals, observability, prompt versioning, and cost/latency budgets
- Collaborate with power systems and GIS specialists to ensure shipping is engineering-grade
- Spend time with customers working alongside Product and Design teams to decide what to build and iterate on viable solutions
- Set standards for how Neara engineers build with AI, including coding agents in internal workflows
The role offers fully flexible working arrangements with a well-stocked office in Redfern, Sydney. Competitive salary and meaningful ESOP provided.
REQUIREMENTS:
Essential:
- 5+ years building and shipping production software with real depth in backend or full-stack product engineering
- Shipped AI features to paying customers in a commercial product and owned them post-launch (not prototypes or hackathons)—real users depended on it, you watched it break and fixed it
- Hands-on experience with LLM product fundamentals: retrieval, context engineering, tool use, agent orchestration, structured output, prompt design
- Evaluation expertise: can describe an eval approach you built, what it caught, and what it missed
- Sound judgment about where AI should and should not be used; instinct to design for failure modes
- Strong product sense and comfort working directly with users and product teams, including expert users who will give blunt feedback
Nice to have:
- Experience shipping into regulated or enterprise environments (data residency, auditability, private deployments, security review)
- Geospatial, 3D, CAD, simulation, or engineering software backgrounds
- Experience with TypeScript/React, Python, Java, Dart, or Rust (depth in your current stack matters more than exact match)
- Utilities, energy, or critical infrastructure domain knowledge
- Current and unrestricted working rights in Australia (visa sponsorship not available)
