Impala Search
Consultant | Software Engineering at Impala Search
Our client is building a fully AI-powered workplace coaching platform that’s redefining how teams interact, learn, and perform – shaping the next frontier in human–AI collaboration. Powered by cutting‑edge research in generative AI, multimodal reasoning, and behavioural simulation, their platform introduces synthetic AI personas that listen, adapt, and challenge in real time. These AI‑driven simulations foster deeper learning, stronger leadership, and sharper decision‑making across entire organisations.
Following a successful pre‑seed round earlier this year, the company is on track to reach profitability by Q1 2026.
Role Overview As a
Founding Full‑Stack Engineer , you’ll be at the core of building an AI‑native product – shaping systems where user input, AI reasoning, behavioural logic, and response generation happen in milliseconds.
Key Responsibilities
Design and build end‑to‑end features across the stack (TypeScript / Python), with a focus on integrating real‑time, multi‑turn AI dialogue into the user experience.
Work closely with AI researchers to productionise LLM‑powered agents, including retrieval‑augmented memory, contextual feedback loops, and behavioural modelling.
Develop core infrastructure to support latency‑sensitive interaction – combining frontend responsiveness with backend reasoning pipelines.
Build robust systems to manage prompt orchestration, token efficiency, streaming inference, and multi‑agent coordination.
Shape technical direction and engineering standards for a high‑growth team tackling some of the hardest problems in AI productisation.
Qualifications
Professional experience with TypeScript and React – familiarity with Next.js is a strong plus.
Backend development in Python, ideally with FastAPI or similar modern web frameworks.
Comfortable designing and consuming REST APIs and webhooks for real‑time system communication.
Hands‑on experience with MongoDB and Redis in production environments.
Confident working with Docker for local development and containerisation.
Familiarity with AI‑enhanced developer tooling such as Cursor, Claude Code, GitHub Copilot, or similar tools.
A product‑minded builder – comfortable navigating early‑stage ambiguity and contributing across the full stack.
Fluency in English.
If you’re excited by the challenge of turning raw LLM outputs into structured, emotionally intelligent experiences – and want to engineer AI products that go beyond novelty to actually improve how people think, act, and lead – we’d love to hear from you.
Seniority level Mid‑Senior level
Employment type Full‑time
Job function Information Technology
Industries IT Services and IT Consulting
#J-18808-Ljbffr
Following a successful pre‑seed round earlier this year, the company is on track to reach profitability by Q1 2026.
Role Overview As a
Founding Full‑Stack Engineer , you’ll be at the core of building an AI‑native product – shaping systems where user input, AI reasoning, behavioural logic, and response generation happen in milliseconds.
Key Responsibilities
Design and build end‑to‑end features across the stack (TypeScript / Python), with a focus on integrating real‑time, multi‑turn AI dialogue into the user experience.
Work closely with AI researchers to productionise LLM‑powered agents, including retrieval‑augmented memory, contextual feedback loops, and behavioural modelling.
Develop core infrastructure to support latency‑sensitive interaction – combining frontend responsiveness with backend reasoning pipelines.
Build robust systems to manage prompt orchestration, token efficiency, streaming inference, and multi‑agent coordination.
Shape technical direction and engineering standards for a high‑growth team tackling some of the hardest problems in AI productisation.
Qualifications
Professional experience with TypeScript and React – familiarity with Next.js is a strong plus.
Backend development in Python, ideally with FastAPI or similar modern web frameworks.
Comfortable designing and consuming REST APIs and webhooks for real‑time system communication.
Hands‑on experience with MongoDB and Redis in production environments.
Confident working with Docker for local development and containerisation.
Familiarity with AI‑enhanced developer tooling such as Cursor, Claude Code, GitHub Copilot, or similar tools.
A product‑minded builder – comfortable navigating early‑stage ambiguity and contributing across the full stack.
Fluency in English.
If you’re excited by the challenge of turning raw LLM outputs into structured, emotionally intelligent experiences – and want to engineer AI products that go beyond novelty to actually improve how people think, act, and lead – we’d love to hear from you.
Seniority level Mid‑Senior level
Employment type Full‑time
Job function Information Technology
Industries IT Services and IT Consulting
#J-18808-Ljbffr