- Experience
- 2 – 5 years
- Pay
- Not disclosed
- Education
- Not specified
- Location
- Remote (India)
- Work mode
- Remote
- Job type
- Full-time
About this role
Dscout sells a UX research platform used by large brands. This engineer improves its AI agents in production, owning the loop of instrumentation, evaluation, experiments and measured business results. The work covers backend services and feedback pipelines as well as prompt and context design.
What you will do
- Own the production improvement loop for agent behavior
- Instrument agent workflows to trace model and tool behavior
- Define quality standards, eval datasets and monitoring
- Investigate why agents underperform
- Ship improvements to prompts, context, tools and decision logic
- Build backend services and feedback pipelines
- Run experiments, replays and staged rollouts
- Partner with Product, Data Science and Sales
What the employer expects
- 2-5 years of software engineering
- LLM features or agents running in production
- Prompt and context engineering fluency
- Experience building evaluation harnesses
- Comfort with non-deterministic behavior
- Experience running A/B tests or staged rollouts
- Track record owning shipped features after launch
- Daily use of AI coding tools
Benefits
- Compensation package with bonus and equity
- Education stipend
- Remote work stipend
Skills
- LLM agents
- Prompt/context engineering
- Evaluation harnesses
- A/B experimentation
- Backend services
- APIs
- LangChain/LangGraph
- MCP
- LLM observability
Apply on the employer's site
The application opens on Dscout careers (Greenhouse). Dev Portal Notes does not collect your application or charge a fee.
Know someone who fits this role?
Applications are handled on the employer's own site.
Prepare for this role
Close the skill gap
Some links on this page may generate a small commission at no extra cost to you.