Sr. Tech Lead, Prod Dev (RAN, AI-Assisted RCA, Design & Development)

What you will do

• Deep, cross-layer RCA on field and lab issues that span multiple modules, correlating evidence across the full stack: → UE logs · PHY logs · DU / MAC / SCH logs · CU / L3 logs · Core logs · Platform logs · RRH logs · System logs · field issues across EMS / system monitoring. Reproduce field/customer issues in the lab on production-like (Friendly-Operator) setups. Investigate code and deliver bug fixes — own the fix through to validation, not just the analysis note. Field-issue investigation with direct customer / field involvement; feed learnings back into design, regression and stability. Feature development driven by design/framework gaps and customer-driven requirements. Use AI tools (Claude / AI-assisted engineering) to accelerate code understanding, log analysis, debugging, correlation and RCA — especially on multi-module problems. Identify scenarios, improve monitoring/validation coverage, and raise the quality bar before issues reach the field.
• Deep, cross-layer RCA on field and lab issues that span multiple modules, correlating evidence across the full stack: → UE logs · PHY logs · DU / MAC / SCH logs · CU / L3 logs · Core logs · Platform logs · RRH logs · System logs · field issues across EMS / system monitoring. - Reproduce field/customer issues in the lab on production-like (Friendly-Operator) setups. - Investigate code and deliver bug fixes — own the fix through to validation, not just the analysis note. - Field-issue investigat

Must-have

• Strong software engineering in C / C++ (and Python for tooling/automation) with the ability to read and fix production RAN stack code.
• Solid wireless/telecom system understanding across 2G / 4G LTE / 5G NSA / SA — RRC, S1AP/NGAP, X2/Xn, PDCP/RLC/MAC scheduling, PHY/FAPI, GTP-U, and the core/platform interfaces.
• Proven debugging & RCA skills: coredumps/gdb, log/PCAP analysis, memory/crash triage, KPI/counter reasoning.
• A system mindset — comfortable reasoning across UE ↔ RAN ↔ Core ↔ Platform ↔ EMS rather than a single layer.
• Willingness and aptitude to work with AI tools as a daily engineering accelerator.
• Ownership attitude: drives Issue → Fix → Validation to closure.
• Good to have
• O-RAN / disaggregated CU-DU, fronthaul (split 7.2), PTP/timing, IPsec/transport exposure.
• Experience with EMS / OSS, Kibana/KPI monitoring, PM counters.
• Prior field / customer-facing deployment or NPI experience.
• Scrum / Agile delivery experience
• What success looks like
• You turn an opaque field escape into a named, proven root cause and a merged fix.
• Your RCA is accurate — the cause you name is the one the fix confirms (evidence-cited, instrumented, graded).
• You reduce field escapes and the RCA load on the core development team.
• You grow into a complete-product System Engineer who can design, reproduce, debug and fix across any layer.
• Why join
• You will work at the center of PW's Prod-Dev transformation — a "Friendly customer in the lab" operating model — using cutting-edge AI-assisted engineering to solve real, multi-layer telecom problems end to end, with direct customer impact and genuine system ownership.

Academic Qualification